def get_gold_labels(self,
cand_lists: List[List[Candidate]],
annotator: Optional[str] = None) -> List[np.ndarray]:
"""Load dense matrix of GoldLabels for each candidate_class.
:param cand_lists: The candidates to get gold labels for.
:type cand_lists: List of list of candidates.
:param annotator: A specific annotator key to get labels for. Default
None.
:type annotator: str
:raises ValueError: If get_gold_labels is called before gold labels are
loaded, the result will contain ABSTAIN values. We raise a
ValueError to help indicate this potential mistake to the user.
:return: A list of MxN dense matrix where M are the candidates and N is the
annotators. If annotator is provided, return a list of Mx1 matrix.
:rtype: list[np.ndarray]
"""
gold_labels = [
unshift_label_matrix(m) for m in get_sparse_matrix(
self.session, GoldLabelKey, cand_lists, key=annotator)
]
for cand_labels in gold_labels:
if ABSTAIN in cand_labels:
raise ValueError("Gold labels contain ABSTAIN labels. "
"Did you load gold labels beforehand?")
return gold_labels
def get_feature_matrices(
self, cand_lists: List[List[Candidate]]) -> List[csr_matrix]:
"""Load sparse matrix of Features for each candidate_class.
:param cand_lists: The candidates to get features for.
:return: A list of MxN sparse matrix where M are the candidates and N is the
features.
"""
return get_sparse_matrix(self.session, FeatureKey, cand_lists)
def get_label_matrices(self, cand_lists):
"""Load sparse matrix of Labels for each candidate_class.
:param cand_lists: The candidates to get labels for.
:type cand_lists: List of list of candidates.
:return: An MxN sparse matrix where M are the candidates and N is the
labeling functions.
:rtype: csr_matrix
"""
return get_sparse_matrix(self.session, LabelKey, cand_lists)
def get_feature_matrices(self, cand_lists):
"""Load sparse matrix of Features for each candidate_class.
:param cand_lists: The candidates to get features for.
:type cand_lists: List of list of candidates.
:return: An MxN sparse matrix where M are the candidates and N is the
features.
:rtype: csr_matrix
"""
return get_sparse_matrix(self.session, FeatureKey, cand_lists)
def get_gold_labels(session, cand_lists, annotator_name="gold"):
"""Get the sparse matrix for the specified annotator.
:param session: The database session.
:param cand_lists: The candidates to get gold labels for.
:type cand_lists: List of list of candidates.
:param annotator: A specific annotator key to get labels for. Default
"gold".
:type annotator: str
"""
return get_sparse_matrix(session, GoldLabelKey, cand_lists, key=annotator_name)
def get_label_matrices(self, cand_lists: List[List[Candidate]]) -> List[np.ndarray]:
"""Load dense matrix of Labels for each candidate_class.
:param cand_lists: The candidates to get labels for.
:return: A list of MxN dense matrix where M are the candidates and N is the
labeling functions.
"""
return [
unshift_label_matrix(m)
for m in get_sparse_matrix(self.session, LabelKey, cand_lists)
]
def get_gold_labels(self, cand_lists, annotator=None):
"""Load sparse matrix of GoldLabels for each candidate_class.
:param cand_lists: The candidates to get gold labels for.
:type cand_lists: List of list of candidates.
:param annotator: A specific annotator key to get labels for. Default
None.
:type annotator: str
:return: An MxN sparse matrix where M are the candidates and N is the
annotators. If annotator is provided, return an Mx1 matrix.
:rtype: csr_matrix
"""
return get_sparse_matrix(self.session, GoldLabelKey, cand_lists, key=annotator)
def get_gold_labels(self,
cand_lists: List[List[Candidate]],
annotator: Optional[str] = None) -> List[np.ndarray]:
"""Load dense matrix of GoldLabels for each candidate_class.
:param cand_lists: The candidates to get gold labels for.
:type cand_lists: List of list of candidates.
:param annotator: A specific annotator key to get labels for. Default
None.
:type annotator: str
:return: A list of MxN dense matrix where M are the candidates and N is the
annotators. If annotator is provided, return a list of Mx1 matrix.
:rtype: list[np.ndarray]
"""
return [
unshift_label_matrix(m) for m in get_sparse_matrix(
self.session, GoldLabelKey, cand_lists, key=annotator)
]
def load_gold_labels(session, cand_lists, annotator_name="gold"):
"""Load the sparse matrix for the specified annotator."""
return get_sparse_matrix(session,
GoldLabelKey,
cand_lists,
key=annotator_name)
def get_label_matrices(self, cand_lists):
"""Load sparse matrix of Labels for each candidate_class."""
return get_sparse_matrix(self.session, LabelKey, cand_lists)
def get_gold_labels(self, cand_lists, annotator=None):
"""Load sparse matrix of GoldLabels for each candidate_class."""
return get_sparse_matrix(self.session,
GoldLabelKey,
cand_lists,
key=annotator)
def get_feature_matrices(self, cand_lists):
"""Load sparse matrix of Features for each candidate_class."""
return get_sparse_matrix(self.session, FeatureKey, cand_lists)
